{ "data": { "a": { "slug": "devstral-small-2", "name": "Devstral Small 2", "vendor": "Mistral AI", "vendorUrl": "https://mistral.ai", "kind": "weights", "category": "open-weights", "summary": "Devstral Small 2 is Mistral's open-weight coding agent model, 24B parameters with image input, tool calling and a 256K context. Apache 2.0. It runs in vLLM, SGLang, Transformers, llama.cpp and Ollama, where the 4-bit build is 15 GB.", "url": "https://www.anchorterminal.com/tools/devstral-small-2", "markdownUrl": "https://www.anchorterminal.com/tools/devstral-small-2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/devstral-small-2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json", "dns": "devstral-small-2.grade.anchorterminal.com", "repo": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "mistralai/Devstral-Small-2-24B-Instruct-2512" }, { "registry": "ollama", "name": "devstral-small-2" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under Apache 2.0. Running it yourself takes 15 GB at Q4_K_M from Ollama's library, 26 GB in FP8 from Mistral, or 26 GB at Q8_0 from ggml-org. Mistral's API serves it too (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "coding", "agentic", "vision", "tool-calling", "long-context", "apache-2.0", "safetensors", "fp8", "gguf", "ollama", "self-hosted" ], "lastRelease": "2026-07-15", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 50, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 65, "reach": 90, "risk": 60, "upkeep": 46 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.", "bestFor": "Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac", "strengths": [ "Runs in vLLM, SGLang, Transformers, llama.cpp and Ollama", "15 GB at 4 bits from Ollama's library", "Apache 2.0, ungated, and on Mistral's API", "Tool calling documented, with test prompts and expected output", "A 256K context with image input" ], "weaknesses": [ "No limitations, safety results, languages or data on the card", "No reasoning mode", "Tool calls one at a time, by the card's own tests", "Released in December 2025, and newer coding models have passed it", "Mistral ships FP8 only. The 4-bit builds are other people's" ], "agentNotes": [ "`ollama run devstral-small-2` is the quickest start, at 15 GB", "On vLLM pass `--tool-call-parser mistral --enable-auto-tool-choice`", "Send the system prompt from CHAT_SYSTEM_PROMPT.txt in the repository. The card says results depend on it", "Use a low temperature. The repository's default is 0.15", "Plan for one tool call per turn", "The same model is on our Mistral API listing if you'd rather not host it" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 65, "reach": 90, "risk": 60, "upkeep": 46 }, "provenanceScore": 84, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "ollama run devstral-small-2\n# or: vllm serve mistralai/Devstral-Small-2-24B-Instruct-2512 --max-model-len 262144 --tool-call-parser mistral --enable-auto-tool-choice", "http": "# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1, and Ollama at http://localhost:11434/v1.\n# Send the system prompt from CHAT_SYSTEM_PROMPT.txt and tools in the OpenAI function format" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/devstral-small-2" }, "sameCompany": [ "mistral-embeddings", "mistral-moderation", "mistral-voxtral-transcribe", "voxtral-mini-4b-realtime-2602", "mistral-ocr", "mistral-vibe-cli", "mistral-large-4" ], "sameModel": [ "mistral-api" ], "weights": { "trainedBy": "Mistral AI", "builtOn": "Mistral-Small-3.1-24B-Base-2503, per the metadata", "params": "24B", "context": 262144, "goodFor": "A coding agent on one 24 GB GPU or a 32 GB Mac: exploring a repository, editing files and calling tools, with screenshots and diagrams as input.", "runtimes": [ "llama.cpp", "Ollama", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Ollama devstral-small-2 (Q4_K_M)", "url": "https://ollama.com/library/devstral-small-2", "who": "ollama", "precision": "q4_k_m", "sizeGB": 15, "memoryGB": 24, "format": "ollama", "runsOn": [ "Ollama" ], "note": "From Ollama's own library, 15 GB as its tags page lists it" }, { "name": "Devstral-Small-2-24B-Instruct-2512 (FP8 safetensors)", "url": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "who": "publisher", "precision": "fp8", "sizeGB": 25.79, "memoryGB": 32, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "Mistral's release precision. The repository holds it in two layouts" }, { "name": "ggml-org Devstral-Small-2-24B-Instruct-2512-GGUF (Q8_0)", "url": "https://huggingface.co/ggml-org/Devstral-Small-2-24B-Instruct-2512-GGUF", "who": "llama.cpp", "precision": "q8_0", "sizeGB": 25.94, "memoryGB": 32, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From ggml-org, the llama.cpp project's organisation. 25.06 GB of Q8_0 weights plus the 0.88 GB F16 projector, from the Hub's model information on 10 November 2026" }, { "name": "Ollama devstral-small-2 (Q8_0)", "url": "https://ollama.com/library/devstral-small-2", "who": "ollama", "precision": "q8_0", "sizeGB": 26, "memoryGB": 32, "format": "ollama", "runsOn": [ "Ollama" ], "note": "From Ollama's own library, 26 GB as its tags page lists it" } ], "run": "ollama run devstral-small-2", "runBuild": "Ollama devstral-small-2 (Q4_K_M)", "checked": "2026-11-10", "minMemoryGB": 24 }, "family": { "lab": "Mistral AI", "family": "Devstral", "url": "https://www.anchorterminal.com/open-weights/#mistral", "olderCount": 49 }, "area": "models", "provenance": { "legalEntity": "Mistral AI (RCS Paris 952 418 325)", "domain": "mistral.ai", "domainRegistered": "2019-05-15", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/commits/main", "securityTxt": "valid", "checked": "2026-11-10", "notes": [ "The files sit in Mistral's verified mistralai organisation. Legal entity, domain and security.txt are carried from our Mistral Large 4 listing.", "Nothing is hosted under this listing, so Apache 2.0 stands in for terms of service and no privacy policy is scored. The Mistral API that serves this model has its own listing.", "The changelog is the commit history, 25 commits from 9 December 2025 to 15 July 2026." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/devstral-small-2.json" }, "answer": "GLM-5.3-Flash scores 65.1 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.", "b": { "slug": "glm-5-3-flash", "name": "GLM-5.3-Flash", "vendor": "Z.ai", "vendorUrl": "https://z.ai", "kind": "weights", "category": "open-weights", "summary": "GLM-5.3-Flash is Z.ai's open-weight multimodal mixture-of-experts model, 320B parameters with 18B active and a 1,048,576-token context, published on Hugging Face in FP8 and BF16 under the MIT licence.", "url": "https://www.anchorterminal.com/tools/glm-5-3-flash", "markdownUrl": "https://www.anchorterminal.com/tools/glm-5-3-flash.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/glm-5-3-flash.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/glm-5-3-flash.json", "dns": "glm-5-3-flash.grade.anchorterminal.com", "repo": "https://huggingface.co/zai-org/GLM-5.3-Flash", "license": "MIT", "transports": [], "packages": [ { "registry": "huggingface", "name": "zai-org/GLM-5.3-Flash" }, { "registry": "huggingface", "name": "zai-org/GLM-5.3-Flash-BF16" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under the MIT licence. Z.ai also sells hosted access as glm-5.3-flash on its own API, which isn't graded here. Running the weights yourself costs the hardware, 328.4 GB for the FP8 files and 642.7 GB for BF16 (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-02" }, "docsUrl": "https://huggingface.co/zai-org/GLM-5.3-Flash", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "multimodal", "reasoning", "tool-calling", "mit", "safetensors", "fp8", "self-hosted" ], "lastRelease": "2026-08-26", "graded": true, "anchor": { "graded": true, "score": 65.1, "grade": "B", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 13, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 75, "interface": 70, "reach": 60, "risk": 55, "upkeep": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-02" }, "negative": 0, "verdict": "An MIT-licensed multimodal agent and coding model with a 1M-token context and several tool calls per turn, served by vLLM, SGLang, llama.cpp and Transformers. Z.ai's smallest build is 328 GB in FP8, so it needs a multi-GPU server. The main risk is that nothing on safety or prompt injection is published and there is no way to report a flaw.", "bestFor": "Teams with a multi-GPU server who want an MIT-licensed multimodal agent model with a 1M-token context, or agents that call it through a hosted provider", "strengths": [ "MIT weights with no use policy, downloadable with no account", "Model code in released llama.cpp b11768, vLLM 0.32.0, SGLang 0.5.22 and Transformers 5.16.1", "Safetensors only, no remote code, files in Z.ai's own organisation with a SHA-256 per shard", "1,048,576 tokens of native context and several tool calls per turn in the chat template", "Chat template changed as recently as 15 October 2026, and hosted by Z.ai and six other providers for agents without the hardware" ], "weaknesses": [ "Z.ai's smallest build is 328.4 GB in FP8, and no Ollama or LM Studio local build exists", "No safety evaluation, agent-use guidance or security contact", "Thinking is always on, and reasoning_effort only lowers it to low", "The tool-call format lives only in the chat template, with the parser named by the runtimes", "The card leaves out intended use, limitations, context length and knowledge cut-off, and no zai-org reply on discussions since 28 September" ], "agentNotes": [ "Start it with `vllm serve zai-org/GLM-5.3-Flash --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser glm47 --reasoning-parser glm47` (vLLM 0.32.0 or later, about 386 GB of GPU memory per vLLM's recipe)", "Use the glm47 tool-call and reasoning parsers in vLLM or SGLang; calls come back as tool_call blocks with arg_key and arg_value pairs", "Pass `chat_template_kwargs: {\"reasoning_effort\": \"low\"}` for short tasks; anything other than low or high falls back to max", "Don't rely on `thinking: false` from SGLang's cookbook, since the template has no such switch and always opens a think block", "Set `clear_thinking: true` in chat use, since the default keeps earlier reasoning in the prompt", "On a 128 GB machine only third-party low-bit builds come near fitting, none of them from Z.ai" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.1 } ], "editorialScores": { "capability": 75, "interface": 70, "reach": 60, "risk": 55, "upkeep": 58 }, "provenanceScore": 61, "checked": { "categories": { "capability": "2026-11-02", "interface": "2026-11-02", "reach": "2026-11-02", "risk": "2026-11-02", "upkeep": "2026-11-02" }, "last": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# vLLM 0.32.0 or later, per vLLM's recipe (FP8, about 386 GB of GPU memory)\nvllm serve zai-org/GLM-5.3-Flash --tensor-parallel-size 4 \\\n --enable-auto-tool-choice --tool-call-parser glm47 --reasoning-parser glm47\n# or, with llama.cpp and llama.cpp's own GGUF:\nllama-server -hf ggml-org/GLM-5.3-Flash-GGUF:Q4_K --jinja", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"zai-org/GLM-5.3-Flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"chat_template_kwargs\": {\"reasoning_effort\": \"low\"}}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/glm-5-3-flash" }, "sameCompany": [ "glm-4-5-air", "glm-4-7-flash", "glm-5-3" ], "weights": { "trainedBy": "Z.ai", "params": "320B", "active": "18B", "context": 1048576, "goodFor": "Multimodal agent and coding model: text, images and video in, text out, with tool calling and always-on reasoning.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "GLM-5.3-Flash-FP4-Local", "url": "https://huggingface.co/nvidia/GLM-5.3-Flash-FP4-Local", "who": "NVIDIA", "precision": "nvfp4", "sizeGB": 177.5, "memoryGB": 256, "format": "safetensors", "note": "NVIDIA's own FP4 build (Model Optimizer), made for NVIDIA Blackwell GPUs such as DGX Spark and RTX PRO 6000; FP4 kernels don't run on the AMD reference machine. Not the publisher's build, so it doesn't count toward Reach's memory item. Size summed from the Hub's file list on 21 October 2026." }, { "name": "GLM-5.3-Flash-NVFP4", "url": "https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4", "who": "NVIDIA", "precision": "nvfp4", "sizeGB": 204.4, "memoryGB": 256, "format": "safetensors", "note": "NVIDIA's own FP4 build (Model Optimizer), made for NVIDIA Blackwell GPUs such as DGX Spark and RTX PRO 6000; FP4 kernels don't run on the AMD reference machine. Not the publisher's build, so it doesn't count toward Reach's memory item. Size summed from the Hub's file list on 21 October 2026." }, { "name": "ggml-org GLM-5.3-Flash-GGUF (Q4_K)", "url": "https://huggingface.co/ggml-org/GLM-5.3-Flash-GGUF", "who": "llama.cpp", "precision": "q4_k", "sizeGB": 182.03, "memoryGB": 256, "format": "gguf", "runsOn": [ "llama.cpp" ], "note": "From ggml-org, the llama.cpp project's organisation. 181.37 GB of Q4_K weights plus the 0.65 GB Q8_0 vision projector, from the Hub's model information on 10 November 2026. The 2-bit files (Q2_K 133.8 GB, Q2_K_S 110.0 GB) are below the 4-bit line and aren't listed. Recorded after the last grading, so Reach doesn't count it yet" }, { "name": "GLM-5.3-Flash", "url": "https://huggingface.co/zai-org/GLM-5.3-Flash", "who": "publisher", "precision": "fp8", "sizeGB": 328.3, "memoryGB": 512, "format": "safetensors" }, { "name": "GLM-5.3-Flash-BF16", "url": "https://huggingface.co/zai-org/GLM-5.3-Flash-BF16", "who": "publisher", "precision": "bf16", "sizeGB": 642.7, "memoryGB": 1024, "format": "safetensors", "runsOn": [ "vLLM (ROCm)", "SGLang (ROCm)" ] } ], "run": "vllm serve zai-org/GLM-5.3-Flash --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser glm47 --reasoning-parser glm47", "runBuild": "GLM-5.3-Flash", "checked": "2026-10-21", "minMemoryGB": 256 }, "family": { "lab": "Z.ai (Zhipu AI)", "family": "GLM-5", "url": "https://www.anchorterminal.com/open-weights/#zai", "others": [ { "name": "GLM-5", "url": "https://huggingface.co/zai-org/GLM-5", "params": "744B-A40B" }, { "name": "GLM-5.1", "url": "https://huggingface.co/zai-org/GLM-5.1", "params": "744B-A40B" }, { "name": "GLM-5.2", "url": "https://huggingface.co/zai-org/GLM-5.2", "params": "744B-A40B" }, { "name": "GLM-5.3", "url": "https://huggingface.co/zai-org/GLM-5.3", "params": "744B-A40B", "listing": "https://www.anchorterminal.com/tools/glm-5-3" } ], "olderCount": 19, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "Z.AI Co., Ltd (named in the licence's copyright line)", "domain": "z.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/zai-org/GLM-5.3-Flash/commits/main", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The LICENSE file reads Copyright (c) 2026 Z.AI Co., Ltd. The registration date of z.ai couldn't be read, since the RDAP service answered 429 on 21 October 2026.", "Nothing is hosted, so the MIT licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history. Early messages say only \"update\"; later ones say what changed (a chat template fix on 4 September, evaluation results on 7 September and 12 October, a chat template speed-up on 15 October).", "z.ai/.well-known/security.txt and docs.z.ai/.well-known/security.txt answered 404 on 21 October 2026." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/glm-5-3-flash.json", "live": { "slug": "glm-5-3-flash", "securityTxt": { "url": "https://z.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-10T16:09:36.154640571Z" }, "domain": { "domain": "z.ai", "registered": "2017-12-15", "source": "https://rdap.identitydigital.services/rdap/domain/z.ai", "checkedAt": "2026-11-08T15:05:18.801433245Z" }, "pages": [ { "url": "https://huggingface.co/zai-org/GLM-5.3-Flash/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:24:02.708352819Z", "changedAt": "2026-11-10T16:24:02.708352819Z", "fingerprint": "108904f1a213" } ], "updatedAt": "2026-11-10T16:24:02.708352819Z" } }, "edges": [ { "by": 30, "category": "reach", "leads": "devstral-small-2", "name": "Reach", "reasons": { "a": "Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.", "b": "Memory earns nothing, since Z.ai's smallest build is the 328.4 GB FP8 one, about 394 GB with the fifth added, and neither Ollama nor LM Studio has a local build (both list it as cloud only). Four runtimes run it in a released version, llama.cpp, vLLM, SGLang and Transformers, for 20, while Ollama and LM Studio don't. Z.ai publishes one quantised build, FP8, for 10. The MIT licence with nothing added gives the full 15, the files download with no account or gate for 10, and Z.ai's own API plus six providers on Hugging Face serve it, for 5." }, "scores": { "a": 90, "b": 60 } }, { "by": 12, "category": "upkeep", "leads": "glm-5-3-flash", "name": "Documentation and upkeep", "reasons": { "a": "Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokenizer and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.", "b": "The card covers architecture, parameters and languages and misses four of the seven items, for 8. Training data is 5, a 30T-token corpus described with no sources or cut-off. The last change, a chat template speed-up on 15 October in both repositories, is within 30 days on 2 November, for 20; Z.ai's GLM-5 GitHub repository has changed only its docs since. Responsiveness is 10, as zai-org answered 14 of the 38 recent discussions others opened (26 August to 30 October), the last on 28 September, which is some but not most. Version policy is 5 for a first release, and file health is the full 10, with files and card agreeing and no broken-file report waiting as far as the research record shows." }, "scores": { "a": 46, "b": 58 } }, { "by": 5, "category": "risk", "leads": "devstral-small-2", "name": "Risk", "reasons": { "a": "File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.", "b": "File safety is full, with safetensors only, no Python and no remote code needed in Transformers 5.16.1 or later. Provenance is full, files in the zai-org organisation Z.ai links from GitHub with a SHA-256 for every shard. Safety evaluation and agent guidance are 0, as nothing is published on either. Licence risk is the full 15, since MIT adds no policy, threshold or changeable terms. The security programme is 0, with no security.txt on z.ai or docs.z.ai, no SECURITY.md on GitHub and no advisories found." }, "scores": { "a": 60, "b": 55 } }, { "by": 5, "category": "interface", "leads": "glm-5-3-flash", "name": "Agent interface", "reasons": { "a": "Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.", "b": "A Jinja chat template sits in both repositories, for 20. The tool-calling format is 10, because it is defined only by the template and the glm47 parser is named by vLLM and SGLang rather than by Z.ai. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and only the hosted API documented for JSON. Reasoning control is 10, a per-request budget through reasoning_effort, with the reasoning coming back in a think block, though thinking can't be turned off. Context is 10, 1,048,576 tokens native with no rotary scaling." }, "scores": { "a": 65, "b": 70 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Mistral AI", "b": "Z.ai", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-07-15", "b": "2026-08-26", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "none", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "GLM-5.3-Flash scores 65.1 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.", "question": "Which is better for AI agents, Devstral Small 2 or GLM-5.3-Flash?" } ], "goodFor": [ { "aheadOn": [ "Reach, 90 against 60", "Risk, 60 against 55" ], "also": null, "goodFor": "Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac", "slug": "devstral-small-2", "watchFor": "No limitations, safety results, languages or data on the card" }, { "aheadOn": [ "Agent interface, 70 against 65", "Documentation and upkeep, 58 against 46" ], "also": null, "goodFor": "Teams with a multi-GPU server who want an MIT-licensed multimodal agent model with a 1M-token context, or agents that call it through a hosted provider", "slug": "glm-5-3-flash", "watchFor": "Z.ai's smallest build is 328.4 GB in FP8, and no Ollama or LM Studio local build exists" } ], "history": null, "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2.json", "title": "Agents-A1-4B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3-flash.json", "title": "Agents-A1-4B vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2.json", "title": "Apertus v1.5 8B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3-flash.json", "title": "Apertus v1.5 8B vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2.json", "title": "Apodex-1.1-mini vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3-flash.json", "title": "Apodex-1.1-mini vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2.json", "title": "Arete-27B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3-flash.json", "title": "Arete-27B vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2.json", "title": "BigBang-v1 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3-flash.json", "title": "BigBang-v1 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2.json", "title": "Carbon-X vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash.json", "title": "Carbon-X vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2.json", "title": "Cola2 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-glm-5-3-flash.json", "title": "Cola2 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/cola2-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.json", "title": "Cosmos-Reason2-2B vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3-flash.json", "title": "Cosmos-Reason2-2B vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2.json", "title": "Darwin-36B-Opus vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3-flash.json", "title": "Darwin-36B-Opus vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.json", "title": "DeepSeek-V3.2 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3-flash.json", "title": "DeepSeek-V3.2 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2.json", "title": "DeepSeek V4.1 Flash vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3-flash.json", "title": "DeepSeek V4.1 Flash vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.json", "title": "DeepSeek-V4-Flash-0731 vs Devstral Small 2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3-flash.json", "title": "DeepSeek-V4-Flash-0731 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it.json", "title": "Devstral Small 2 vs DiffusionGemma 26B A4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b.json", "title": "Devstral Small 2 vs EXAONE 4.5 33B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it.json", "title": "Devstral Small 2 vs Gemma 4 12B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it.json", "title": "Devstral Small 2 vs Gemma 4 26B A4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it.json", "title": "Devstral Small 2 vs Gemma 4 31B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it.json", "title": "Devstral Small 2 vs Gemma 4 E2B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it.json", "title": "Devstral Small 2 vs Gemma 4 E4B IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air.json", "title": "Devstral Small 2 vs GLM-4.5-Air", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash.json", "title": "Devstral Small 2 vs GLM-4.7-Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.json", "title": "Devstral Small 2 vs GLM-5.3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b.json", "title": "Devstral Small 2 vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b.json", "title": "Devstral Small 2 vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-30b.json", "title": "Devstral Small 2 vs Granite 4.2 30B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-30b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b.json", "title": "Devstral Small 2 vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b.json", "title": "Devstral Small 2 vs Granite 4.2 8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b.json", "title": "Devstral Small 2 vs Hy-Memory-30B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.json", "title": "Devstral Small 2 vs Hy3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.json", "title": "Devstral Small 2 vs Inkling", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small.json", "title": "Devstral Small 2 vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Devstral Small 2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.json", "title": "Devstral Small 2 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro.json", "title": "Devstral Small 2 vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1.json", "title": "Devstral Small 2 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos.json", "title": "Devstral Small 2 vs Kronos", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1.json", "title": "Devstral Small 2 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.json", "title": "Devstral Small 2 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1.json", "title": "Devstral Small 2 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.json", "title": "Devstral Small 2 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b.json", "title": "Devstral Small 2 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.json", "title": "Devstral Small 2 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.json", "title": "Devstral Small 2 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b.json", "title": "Devstral Small 2 vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b.json", "title": "Devstral Small 2 vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny.json", "title": "Devstral Small 2 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019.json", "title": "Devstral Small 2 vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.json", "title": "Devstral Small 2 vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl.json", "title": "Devstral Small 2 vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5.json", "title": "Devstral Small 2 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b.json", "title": "Devstral Small 2 vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b.json", "title": "Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b.json", "title": "Devstral Small 2 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5.json", "title": "Devstral Small 2 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7.json", "title": "Devstral Small 2 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash.json", "title": "Devstral Small 2 vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4.json", "title": "Devstral Small 2 vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b.json", "title": "Devstral Small 2 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b.json", "title": "Devstral Small 2 vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.json", "title": "Devstral Small 2 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Devstral Small 2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Devstral Small 2 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b.json", "title": "Devstral Small 2 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b.json", "title": "Devstral Small 2 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Devstral Small 2 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b.json", "title": "Devstral Small 2 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b.json", "title": "Devstral Small 2 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0.json", "title": "Devstral Small 2 vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0.json", "title": "Devstral Small 2 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think.json", "title": "Devstral Small 2 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b.json", "title": "Devstral Small 2 vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b.json", "title": "Devstral Small 2 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b.json", "title": "Devstral Small 2 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b.json", "title": "Devstral Small 2 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it.json", "title": "Devstral Small 2 vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b.json", "title": "Devstral Small 2 vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Devstral Small 2 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507.json", "title": "Devstral Small 2 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b.json", "title": "Devstral Small 2 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b.json", "title": "Devstral Small 2 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b.json", "title": "Devstral Small 2 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b.json", "title": "Devstral Small 2 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b.json", "title": "Devstral Small 2 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b.json", "title": "Devstral Small 2 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b.json", "title": "Devstral Small 2 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b.json", "title": "Devstral Small 2 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b.json", "title": "Devstral Small 2 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next.json", "title": "Devstral Small 2 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next.json", "title": "Devstral Small 2 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct.json", "title": "Devstral Small 2 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2.json", "title": "Devstral Small 2 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint.json", "title": "Devstral Small 2 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview.json", "title": "Devstral Small 2 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview.json", "title": "Devstral Small 2 vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b.json", "title": "Devstral Small 2 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b.json", "title": "Devstral Small 2 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash.json", "title": "Devstral Small 2 vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b.json", "title": "Devstral Small 2 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Devstral Small 2 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b.json", "title": "Devstral Small 2 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2.json", "title": "Devstral Small 2 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b.json", "title": "Devstral Small 2 vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b.json", "title": "Devstral Small 2 vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b.json", "title": "Devstral Small 2 vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash.json", "title": "DiffusionGemma 26B A4B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3-flash.json", "title": "EXAONE 4.5 33B vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 12B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 26B A4B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 31B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 E2B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3-flash.json", "title": "Gemma 4 E4B IT vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3-flash.json", "title": "GLM-4.5-Air vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3-flash.json", "title": "GLM-4.7-Flash vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-120b.json", "title": "GLM-5.3-Flash vs gpt-oss-120b", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-120b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b.json", "title": "GLM-5.3-Flash vs gpt-oss-20b", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-30b.json", "title": "GLM-5.3-Flash vs Granite 4.2 30B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-30b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-3b.json", "title": "GLM-5.3-Flash vs Granite 4.2 3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-8b.json", "title": "GLM-5.3-Flash vs Granite 4.2 8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-8b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy-memory-30b-a3b.json", "title": "GLM-5.3-Flash vs Hy-Memory-30B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy-memory-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3.json", "title": "GLM-5.3-Flash vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.json", "title": "GLM-5.3-Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-small.json", "title": "GLM-5.3-Flash vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "GLM-5.3-Flash vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3.json", "title": "GLM-5.3-Flash vs Kimi K3", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3-1-pro.json", "title": "GLM-5.3-Flash vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1.json", "title": "GLM-5.3-Flash vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kronos.json", "title": "GLM-5.3-Flash vs Kronos", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-m-1.json", "title": "GLM-5.3-Flash vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-s-2-1.json", "title": "GLM-5.3-Flash vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-xs-2-1.json", "title": "GLM-5.3-Flash vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b.json", "title": "GLM-5.3-Flash vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm2-5-2-6b.json", "title": "GLM-5.3-Flash vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b.json", "title": "GLM-5.3-Flash vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b.json", "title": "GLM-5.3-Flash vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-omni-2b.json", "title": "GLM-5.3-Flash vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-vl-2b.json", "title": "GLM-5.3-Flash vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-0-tiny.json", "title": "GLM-5.3-Flash vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-1-flash-1019.json", "title": "GLM-5.3-Flash vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-longcat-2-5.json", "title": "GLM-5.3-Flash vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-distill-qwen-9b.json", "title": "GLM-5.3-Flash vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-flash-rl.json", "title": "GLM-5.3-Flash vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-o-4-5.json", "title": "GLM-5.3-Flash vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-1b.json", "title": "GLM-5.3-Flash vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-35b-a3b.json", "title": "GLM-5.3-Flash vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm5-2b.json", "title": "GLM-5.3-Flash vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-5.json", "title": "GLM-5.3-Flash vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-7.json", "title": "GLM-5.3-Flash vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m3-1-flash.json", "title": "GLM-5.3-Flash vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mistral-large-4.json", "title": "GLM-5.3-Flash vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-muse-glimmer-30b.json", "title": "GLM-5.3-Flash vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-2-3b.json", "title": "GLM-5.3-Flash vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b.json", "title": "GLM-5.3-Flash vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "GLM-5.3-Flash vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "GLM-5.3-Flash vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-30b-a3b.json", "title": "GLM-5.3-Flash vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-4b.json", "title": "GLM-5.3-Flash vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "GLM-5.3-Flash vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-super-120b-a12b.json", "title": "GLM-5.3-Flash vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-ultra-550b-a55b.json", "title": "GLM-5.3-Flash vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-north-mini-code-1-0.json", "title": "GLM-5.3-Flash vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-occamy-1-0.json", "title": "GLM-5.3-Flash vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-olmo-3-7b-think.json", "title": "GLM-5.3-Flash vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-122b.json", "title": "GLM-5.3-Flash vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-35b-a3b.json", "title": "GLM-5.3-Flash vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-397b.json", "title": "GLM-5.3-Flash vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-9b.json", "title": "GLM-5.3-Flash vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-otel-2-0-llm-31b-it.json", "title": "GLM-5.3-Flash vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen-agentworld-35b-a3b.json", "title": "GLM-5.3-Flash vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-30b-a3b-instruct-2507.json", "title": "GLM-5.3-Flash vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-4b-instruct-2507.json", "title": "GLM-5.3-Flash vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-0-8b.json", "title": "GLM-5.3-Flash vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-122b-a10b.json", "title": "GLM-5.3-Flash vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-2b.json", "title": "GLM-5.3-Flash vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-397b-a17b.json", "title": "GLM-5.3-Flash vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-4b.json", "title": "GLM-5.3-Flash vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-9b.json", "title": "GLM-5.3-Flash vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-27b.json", "title": "GLM-5.3-Flash vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-35b-a3b.json", "title": "GLM-5.3-Flash vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-27b.json", "title": "GLM-5.3-Flash vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-flash-next.json", "title": "GLM-5.3-Flash vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-30b-a3b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-next.json", "title": "GLM-5.3-Flash vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-omni-30b-a3b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-2b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-30b-a3b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-32b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-4b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-8b-instruct.json", "title": "GLM-5.3-Flash vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwopus3-8-27b-flash-v2.json", "title": "GLM-5.3-Flash vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint.json", "title": "GLM-5.3-Flash vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview.json", "title": "GLM-5.3-Flash vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-sensenova-loop-9b-preview.json", "title": "GLM-5.3-Flash vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-smollm3-3b.json", "title": "GLM-5.3-Flash vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-spark-x2-6-4b.json", "title": "GLM-5.3-Flash vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-step-3-7-flash.json", "title": "GLM-5.3-Flash vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-27b.json", "title": "GLM-5.3-Flash vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-flash-next.json", "title": "GLM-5.3-Flash vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-thinkingcap-qwen3-8-27b.json", "title": "GLM-5.3-Flash vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2.json", "title": "GLM-5.3-Flash vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-2b.json", "title": "GLM-5.3-Flash vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-4b.json", "title": "GLM-5.3-Flash vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-zaya1-8b.json", "title": "GLM-5.3-Flash vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash.json", "title": "GLM-5.3 vs GLM-5.3-Flash", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 30, "devstral-small-2": 90, "edge": "devstral-small-2", "glm-5-3-flash": 60, "key": "reach", "name": "Reach", "weight": 25 }, { "by": 5, "devstral-small-2": 60, "edge": "devstral-small-2", "glm-5-3-flash": 55, "key": "risk", "name": "Risk", "weight": 20 }, { "by": 5, "devstral-small-2": 65, "edge": "glm-5-3-flash", "glm-5-3-flash": 70, "key": "interface", "name": "Agent interface", "weight": 10 }, { "by": 12, "devstral-small-2": 46, "edge": "glm-5-3-flash", "glm-5-3-flash": 58, "key": "upkeep", "name": "Documentation and upkeep", "weight": 10 } ], "summary": "GLM-5.3-Flash scores 65.1 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "devstral-small-2": "The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.", "glm-5-3-flash": "An MIT-licensed multimodal agent and coding model with a 1M-token context and several tool calls per turn, served by vLLM, SGLang, llama.cpp and Transformers. Z.ai's smallest build is 328 GB in FP8, so it needs a multi-GPU server. The main risk is that nothing on safety or prompt injection is published and there is no way to report a flaw." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash", "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.min.md" }, "markdown": "GLM-5.3-Flash scores 65.1 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk. Both do open-weight models you run yourself.\n\n- Devstral Small 2: grade C, 61/100, rank #60 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/devstral-small-2.md · JSON https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json\n- GLM-5.3-Flash: grade B, 65.1/100, rank #18 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/glm-5-3-flash.md · JSON https://www.anchorterminal.com/api/v1/tools/glm-5-3-flash.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 6359 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Devstral Small 2 (C)\n\nGood for: Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac\n\nAhead on:\n- Reach, 90 against 60\n- Risk, 60 against 55\n\nWatch for: No limitations, safety results, languages or data on the card\n\n### GLM-5.3-Flash (B)\n\nGood for: Teams with a multi-GPU server who want an MIT-licensed multimodal agent model with a 1M-token context, or agents that call it through a hosted provider\n\nAhead on:\n- Agent interface, 70 against 65\n- Documentation and upkeep, 58 against 46\n\nWatch for: Z.ai's smallest build is 328.4 GB in FP8, and no Ollama or LM Studio local build exists\n\n\n## Why the edge\n\n### Reach: Devstral Small 2 +30\n\n- Devstral Small 2 (90): Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB. Mistral's own FP8 files are 25.79 GB. Runtimes 25, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the mistral3 model, llama.cpp b12242 has the architecture with a GGUF from its own organisation, and Ollama's library has devstral-small-2. Builds 10, one quantised precision from Mistral, the FP8 weights it releases. Terms 15, Apache 2.0 in the card's metadata and text, an OSI licence with nothing added. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Mistral's own API serves Devstral Small 2: the card says the model is available through its API and points there when a local runtime underperforms. 25 + 25 + 10 + 15 + 10 + 5 = 90.\n- GLM-5.3-Flash (60): Memory earns nothing, since Z.ai's smallest build is the 328.4 GB FP8 one, about 394 GB with the fifth added, and neither Ollama nor LM Studio has a local build (both list it as cloud only). Four runtimes run it in a released version, llama.cpp, vLLM, SGLang and Transformers, for 20, while Ollama and LM Studio don't. Z.ai publishes one quantised build, FP8, for 10. The MIT licence with nothing added gives the full 15, the files download with no account or gate for 10, and Z.ai's own API plus six providers on Hugging Face serve it, for 5.\n\n### Documentation and upkeep: GLM-5.3-Flash +12\n\n- Devstral Small 2 (46): Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the last commit, on 15 July 2026, updated the files to match mistral-common, 118 days before this check and within 180. Responsiveness 10, Of the 23 most recent discussions that aren't pull requests (9 December 2025 to 6 November 2026), 11 have a reply from a mistralai member, which is some. Version policy 5, Devstral Small 1.1 stays in its own repository, which this card links as the predecessor, with no dated note on the older card that we read. File health 10, Config, template, tokenizer and card agree, and the June and July commits fixed stray tokens and brought the files in line with mistral-common. 11 + 0 + 10 + 10 + 5 + 10 = 46.\n- GLM-5.3-Flash (58): The card covers architecture, parameters and languages and misses four of the seven items, for 8. Training data is 5, a 30T-token corpus described with no sources or cut-off. The last change, a chat template speed-up on 15 October in both repositories, is within 30 days on 2 November, for 20; Z.ai's GLM-5 GitHub repository has changed only its docs since. Responsiveness is 10, as zai-org answered 14 of the 38 recent discussions others opened (26 August to 30 October), the last on 28 September, which is some but not most. Version policy is 5 for a first release, and file health is the full 10, with files and card agreeing and no broken-file report waiting as far as the research record shows.\n\n### Risk: Devstral Small 2 +5\n\n- Devstral Small 2 (60): File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, files in Mistral's verified mistralai organisation, which Mistral's site links to per our Mistral Large 4 listing (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, mistral.ai's security.txt gives a security contact and a submission policy, as read for the Mistral Large 4 listing (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.\n- GLM-5.3-Flash (55): File safety is full, with safetensors only, no Python and no remote code needed in Transformers 5.16.1 or later. Provenance is full, files in the zai-org organisation Z.ai links from GitHub with a SHA-256 for every shard. Safety evaluation and agent guidance are 0, as nothing is published on either. Licence risk is the full 15, since MIT adds no policy, threshold or changeable terms. The security programme is 0, with no security.txt on z.ai or docs.z.ai, no SECURITY.md on GitHub and no advisories found.\n\n### Agent interface: GLM-5.3-Flash +5\n\n- Devstral Small 2 (65): Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common. Tool-calling format 25, the card documents tools in the OpenAI function format with an example, names the mistral tool-call parser with auto tool choice for vLLM, shows the same for SGLang, and ships test prompts with the expected tool-call output. Trained tool calling 10, the card says the model excels at using tools, and its tests cover one tool call and calls made one at a time in sequence. Structured output 0, Nothing on the card about JSON or schema-constrained answers for this model. Reasoning control 0, no reasoning mode is documented, and a June 2026 commit removed stray thinking tokens from the files. Context 10, 256K tokens per the card, served at 262,144 in its vLLM command. 20 + 25 + 10 + 0 + 0 + 10 = 65.\n- GLM-5.3-Flash (70): A Jinja chat template sits in both repositories, for 20. The tool-calling format is 10, because it is defined only by the template and the glm47 parser is named by vLLM and SGLang rather than by Z.ai. The template takes several calls in one turn, for 20. Structured output is 0, with nothing on the card and only the hosted API documented for JSON. Reasoning control is 10, a per-request budget through reasoning_effort, with the reasoning coming back in a think block, though thinking can't be turned off. Context is 10, 1,048,576 tokens native with no rotary scaling.\n\n## Score by category\n\n| Category | Weight | Devstral Small 2 | GLM-5.3-Flash | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 90 | 60 | Devstral Small 2 +30 |\n| Risk | 20% (20 this run) | 60 | 55 | Devstral Small 2 +5 |\n| Agent interface | 10% (10 this run) | 65 | 70 | GLM-5.3-Flash +5 |\n| Documentation and upkeep | 10% (10 this run) | 46 | 58 | GLM-5.3-Flash +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61 · C** | **65.1 · B** | |\n\n## Facts side by side\n\n| Fact | Devstral Small 2 | GLM-5.3-Flash |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Mistral AI | Z.ai |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-07-15 | 2026-08-26 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | none | 2.8/5 (4) |\n\n## Verdicts\n\n**Devstral Small 2.** The easy one to run: a 24B coding agent under Apache 2.0 that five runtimes carry, 15 GB at 4 bits in Ollama, with a 256K context, image input and well-documented tool calling. It's eleven months old, calls tools one at a time, has no reasoning mode, and its card says nothing on limits, safety or data.\n\n**GLM-5.3-Flash.** An MIT-licensed multimodal agent and coding model with a 1M-token context and several tool calls per turn, served by vLLM, SGLang, llama.cpp and Transformers. Z.ai's smallest build is 328 GB in FP8, so it needs a multi-GPU server. The main risk is that nothing on safety or prompt injection is published and there is no way to report a flaw.\n\n## Before you call either\n\n### Devstral Small 2\n\n1. `ollama run devstral-small-2` is the quickest start, at 15 GB\n2. On vLLM pass `--tool-call-parser mistral --enable-auto-tool-choice`\n3. Send the system prompt from CHAT_SYSTEM_PROMPT.txt in the repository. The card says results depend on it\n4. Use a low temperature. The repository's default is 0.15\n5. Plan for one tool call per turn\n6. The same model is on our Mistral API listing if you'd rather not host it\n\n### GLM-5.3-Flash\n\n1. Start it with `vllm serve zai-org/GLM-5.3-Flash --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser glm47 --reasoning-parser glm47` (vLLM 0.32.0 or later, about 386 GB of GPU memory per vLLM's recipe)\n2. Use the glm47 tool-call and reasoning parsers in vLLM or SGLang; calls come back as tool_call blocks with arg_key and arg_value pairs\n3. Pass `chat_template_kwargs: {\"reasoning_effort\": \"low\"}` for short tasks; anything other than low or high falls back to max\n4. Don't rely on `thinking: false` from SGLang's cookbook, since the template has no such switch and always opens a think block\n5. Set `clear_thinking: true` in chat use, since the default keeps earlier reasoning in the prompt\n6. On a 128 GB machine only third-party low-bit builds come near fitting, none of them from Z.ai\n\n## Questions\n\n### Which is better for AI agents, Devstral Small 2 or GLM-5.3-Flash?\n\nGLM-5.3-Flash scores 65.1 (B) on agent readiness against Devstral Small 2's 61 (C), and leads in 2 of 4 scored categories. Devstral Small 2 leads on reach and risk.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.json, and with the fewest tokens: https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"devstral-small-2\", \"b\": \"glm-5-3-flash\"}`. From a terminal: `anchor compare devstral-small-2 glm-5-3-flash`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/devstral-small-2.json and https://www.anchorterminal.com/api/v1/tools/glm-5-3-flash.json\n\n## Other comparisons with Devstral Small 2 or GLM-5.3-Flash\n\n- [Agents-A1-4B vs Devstral Small 2](https://www.anchorterminal.com/compare/agents-a1-4b-vs-devstral-small-2.md)\n- [Agents-A1-4B vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/agents-a1-4b-vs-glm-5-3-flash.md)\n- [Apertus v1.5 8B vs Devstral Small 2](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-devstral-small-2.md)\n- [Apertus v1.5 8B vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-glm-5-3-flash.md)\n- [Apodex-1.1-mini vs Devstral Small 2](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-devstral-small-2.md)\n- [Apodex-1.1-mini vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-glm-5-3-flash.md)\n- [Arete-27B vs Devstral Small 2](https://www.anchorterminal.com/compare/arete-27b-vs-devstral-small-2.md)\n- [Arete-27B vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/arete-27b-vs-glm-5-3-flash.md)\n- [BigBang-v1 vs Devstral Small 2](https://www.anchorterminal.com/compare/bigbang-v1-vs-devstral-small-2.md)\n- [BigBang-v1 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/bigbang-v1-vs-glm-5-3-flash.md)\n- [Carbon-X vs Devstral Small 2](https://www.anchorterminal.com/compare/carbon-x-vs-devstral-small-2.md)\n- [Carbon-X vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/carbon-x-vs-glm-5-3-flash.md)\n- [Cola2 vs Devstral Small 2](https://www.anchorterminal.com/compare/cola2-vs-devstral-small-2.md)\n- [Cola2 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/cola2-vs-glm-5-3-flash.md)\n- [Cosmos-Reason2-2B vs Devstral Small 2](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-devstral-small-2.md)\n- [Cosmos-Reason2-2B vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-glm-5-3-flash.md)\n- [Darwin-36B-Opus vs Devstral Small 2](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2.md)\n- [Darwin-36B-Opus vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-glm-5-3-flash.md)\n- [DeepSeek-V3.2 vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.md)\n- [DeepSeek-V3.2 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-glm-5-3-flash.md)\n- [DeepSeek V4.1 Flash vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-devstral-small-2.md)\n- [DeepSeek V4.1 Flash vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-glm-5-3-flash.md)\n- [DeepSeek-V4-Flash-0731 vs Devstral Small 2](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.md)\n- [DeepSeek-V4-Flash-0731 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-glm-5-3-flash.md)\n- [Devstral Small 2 vs DiffusionGemma 26B A4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-diffusiongemma-26b-a4b-it.md)\n- [Devstral Small 2 vs EXAONE 4.5 33B](https://www.anchorterminal.com/compare/devstral-small-2-vs-exaone-4-5-33b.md)\n- [Devstral Small 2 vs Gemma 4 12B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-12b-it.md)\n- [Devstral Small 2 vs Gemma 4 26B A4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-26b-a4b-it.md)\n- [Devstral Small 2 vs Gemma 4 31B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-31b-it.md)\n- [Devstral Small 2 vs Gemma 4 E2B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e2b-it.md)\n- [Devstral Small 2 vs Gemma 4 E4B IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-gemma-4-e4b-it.md)\n- [Devstral Small 2 vs GLM-4.5-Air](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-5-air.md)\n- [Devstral Small 2 vs GLM-4.7-Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-4-7-flash.md)\n- [Devstral Small 2 vs GLM-5.3](https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3.md)\n- [Devstral Small 2 vs gpt-oss-120b](https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-120b.md)\n- [Devstral Small 2 vs gpt-oss-20b](https://www.anchorterminal.com/compare/devstral-small-2-vs-gpt-oss-20b.md)\n- [Devstral Small 2 vs Granite 4.2 30B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-30b.md)\n- [Devstral Small 2 vs Granite 4.2 3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-3b.md)\n- [Devstral Small 2 vs Granite 4.2 8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-granite-4-2-8b.md)\n- [Devstral Small 2 vs Hy-Memory-30B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-hy-memory-30b-a3b.md)\n- [Devstral Small 2 vs Hy3](https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.md)\n- [Devstral Small 2 vs Inkling](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling.md)\n- [Devstral Small 2 vs Inkling-Small](https://www.anchorterminal.com/compare/devstral-small-2-vs-inkling-small.md)\n- [Devstral Small 2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Devstral Small 2 vs Kimi K3](https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3.md)\n- [Devstral Small 2 vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/devstral-small-2-vs-kimi-k3-1-pro.md)\n- [Devstral Small 2 vs Kolibri-1](https://www.anchorterminal.com/compare/devstral-small-2-vs-kolibri-1.md)\n- [Devstral Small 2 vs Kronos](https://www.anchorterminal.com/compare/devstral-small-2-vs-kronos.md)\n- [Devstral Small 2 vs Laguna M.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-m-1.md)\n- [Devstral Small 2 vs Laguna S 2.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.md)\n- [Devstral Small 2 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-xs-2-1.md)\n- [Devstral Small 2 vs LBS-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lbs-27b.md)\n- [Devstral Small 2 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm2-5-2-6b.md)\n- [Devstral Small 2 vs LFM3-1.7B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.md)\n- [Devstral Small 2 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-audio-2b.md)\n- [Devstral Small 2 vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-omni-2b.md)\n- [Devstral Small 2 vs LFM3-VL-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-vl-2b.md)\n- [Devstral Small 2 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-0-tiny.md)\n- [Devstral Small 2 vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/devstral-small-2-vs-ling-3-1-flash-1019.md)\n- [Devstral Small 2 vs LongCat-2.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.md)\n- [Devstral Small 2 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Devstral Small 2 vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/devstral-small-2-vs-mimo-v2-6-flash-rl.md)\n- [Devstral Small 2 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-o-4-5.md)\n- [Devstral Small 2 vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-1b.md)\n- [Devstral Small 2 vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm-v-4-7-35b-a3b.md)\n- [Devstral Small 2 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-minicpm5-2b.md)\n- [Devstral Small 2 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-5.md)\n- [Devstral Small 2 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m2-7.md)\n- [Devstral Small 2 vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-minimax-m3-1-flash.md)\n- [Devstral Small 2 vs Mistral Large 4](https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4.md)\n- [Devstral Small 2 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/devstral-small-2-vs-muse-glimmer-30b.md)\n- [Devstral Small 2 vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-2-3b.md)\n- [Devstral Small 2 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nanbeige-4-3-33b.md)\n- [Devstral Small 2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Devstral Small 2 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-30b-a3b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-4b.md)\n- [Devstral Small 2 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Devstral Small 2 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-super-120b-a12b.md)\n- [Devstral Small 2 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/devstral-small-2-vs-nemotron-3-ultra-550b-a55b.md)\n- [Devstral Small 2 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/devstral-small-2-vs-north-mini-code-1-0.md)\n- [Devstral Small 2 vs occamy-1.0](https://www.anchorterminal.com/compare/devstral-small-2-vs-occamy-1-0.md)\n- [Devstral Small 2 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think.md)\n- [Devstral Small 2 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-122b.md)\n- [Devstral Small 2 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-35b-a3b.md)\n- [Devstral Small 2 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-397b.md)\n- [Devstral Small 2 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-ornith-1-5-9b.md)\n- [Devstral Small 2 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/devstral-small-2-vs-otel-2-0-llm-31b-it.md)\n- [Devstral Small 2 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen-agentworld-35b-a3b.md)\n- [Devstral Small 2 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Devstral Small 2 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-4b-instruct-2507.md)\n- [Devstral Small 2 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-0-8b.md)\n- [Devstral Small 2 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-122b-a10b.md)\n- [Devstral Small 2 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-2b.md)\n- [Devstral Small 2 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-397b-a17b.md)\n- [Devstral Small 2 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-4b.md)\n- [Devstral Small 2 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-5-9b.md)\n- [Devstral Small 2 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-27b.md)\n- [Devstral Small 2 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-6-35b-a3b.md)\n- [Devstral Small 2 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-27b.md)\n- [Devstral Small 2 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-8-flash-next.md)\n- [Devstral Small 2 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-coder-next.md)\n- [Devstral Small 2 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-2b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-32b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-4b-instruct.md)\n- [Devstral Small 2 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwen3-vl-8b-instruct.md)\n- [Devstral Small 2 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/devstral-small-2-vs-qwopus3-8-27b-flash-v2.md)\n- [Devstral Small 2 vs Recursive Flint](https://www.anchorterminal.com/compare/devstral-small-2-vs-recursive-flint.md)\n- [Devstral Small 2 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-ripple-65b-preview.md)\n- [Devstral Small 2 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/devstral-small-2-vs-sensenova-loop-9b-preview.md)\n- [Devstral Small 2 vs SmolLM3-3B](https://www.anchorterminal.com/compare/devstral-small-2-vs-smollm3-3b.md)\n- [Devstral Small 2 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-spark-x2-6-4b.md)\n- [Devstral Small 2 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/devstral-small-2-vs-step-3-7-flash.md)\n- [Devstral Small 2 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-27b.md)\n- [Devstral Small 2 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/devstral-small-2-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Devstral Small 2 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/devstral-small-2-vs-thinkingcap-qwen3-8-27b.md)\n- [Devstral Small 2 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/devstral-small-2-vs-unlimited-ocr-2.md)\n- [Devstral Small 2 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-2b.md)\n- [Devstral Small 2 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/devstral-small-2-vs-wevisone-vl-4b.md)\n- [Devstral Small 2 vs ZAYA1-8B](https://www.anchorterminal.com/compare/devstral-small-2-vs-zaya1-8b.md)\n- [DiffusionGemma 26B A4B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-glm-5-3-flash.md)\n- [EXAONE 4.5 33B vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-glm-5-3-flash.md)\n- [Gemma 4 12B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-glm-5-3-flash.md)\n- [Gemma 4 26B A4B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-glm-5-3-flash.md)\n- [Gemma 4 31B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-glm-5-3-flash.md)\n- [Gemma 4 E2B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-glm-5-3-flash.md)\n- [Gemma 4 E4B IT vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-glm-5-3-flash.md)\n- [GLM-4.5-Air vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/glm-4-5-air-vs-glm-5-3-flash.md)\n- [GLM-4.7-Flash vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-glm-5-3-flash.md)\n- [GLM-5.3-Flash vs gpt-oss-120b](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-120b.md)\n- [GLM-5.3-Flash vs gpt-oss-20b](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-gpt-oss-20b.md)\n- [GLM-5.3-Flash vs Granite 4.2 30B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-30b.md)\n- [GLM-5.3-Flash vs Granite 4.2 3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-3b.md)\n- [GLM-5.3-Flash vs Granite 4.2 8B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-granite-4-2-8b.md)\n- [GLM-5.3-Flash vs Hy-Memory-30B-A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy-memory-30b-a3b.md)\n- [GLM-5.3-Flash vs Hy3](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3.md)\n- [GLM-5.3-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.md)\n- [GLM-5.3-Flash vs Inkling-Small](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling-small.md)\n- [GLM-5.3-Flash vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [GLM-5.3-Flash vs Kimi K3](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3.md)\n- [GLM-5.3-Flash vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kimi-k3-1-pro.md)\n- [GLM-5.3-Flash vs Kolibri-1](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kolibri-1.md)\n- [GLM-5.3-Flash vs Kronos](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-kronos.md)\n- [GLM-5.3-Flash vs Laguna M.1](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-m-1.md)\n- [GLM-5.3-Flash vs Laguna S 2.1](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-s-2-1.md)\n- [GLM-5.3-Flash vs Laguna XS 2.1](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-laguna-xs-2-1.md)\n- [GLM-5.3-Flash vs LBS-27B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b.md)\n- [GLM-5.3-Flash vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm2-5-2-6b.md)\n- [GLM-5.3-Flash vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b.md)\n- [GLM-5.3-Flash vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-audio-2b.md)\n- [GLM-5.3-Flash vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-omni-2b.md)\n- [GLM-5.3-Flash vs LFM3-VL-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-vl-2b.md)\n- [GLM-5.3-Flash vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-0-tiny.md)\n- [GLM-5.3-Flash vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ling-3-1-flash-1019.md)\n- [GLM-5.3-Flash vs LongCat-2.5](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-longcat-2-5.md)\n- [GLM-5.3-Flash vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-distill-qwen-9b.md)\n- [GLM-5.3-Flash vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mimo-v2-6-flash-rl.md)\n- [GLM-5.3-Flash vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-o-4-5.md)\n- [GLM-5.3-Flash vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-1b.md)\n- [GLM-5.3-Flash vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm-v-4-7-35b-a3b.md)\n- [GLM-5.3-Flash vs MiniCPM5-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minicpm5-2b.md)\n- [GLM-5.3-Flash vs MiniMax-M2.5](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-5.md)\n- [GLM-5.3-Flash vs MiniMax-M2.7](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m2-7.md)\n- [GLM-5.3-Flash vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-minimax-m3-1-flash.md)\n- [GLM-5.3-Flash vs Mistral Large 4](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-mistral-large-4.md)\n- [GLM-5.3-Flash vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-muse-glimmer-30b.md)\n- [GLM-5.3-Flash vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-2-3b.md)\n- [GLM-5.3-Flash vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b.md)\n- [GLM-5.3-Flash vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [GLM-5.3-Flash vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [GLM-5.3-Flash vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-30b-a3b.md)\n- [GLM-5.3-Flash vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-4b.md)\n- [GLM-5.3-Flash vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [GLM-5.3-Flash vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-super-120b-a12b.md)\n- [GLM-5.3-Flash vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nemotron-3-ultra-550b-a55b.md)\n- [GLM-5.3-Flash vs North Mini Code 1.0](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-north-mini-code-1-0.md)\n- [GLM-5.3-Flash vs occamy-1.0](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-occamy-1-0.md)\n- [GLM-5.3-Flash vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-olmo-3-7b-think.md)\n- [GLM-5.3-Flash vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-122b.md)\n- [GLM-5.3-Flash vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-35b-a3b.md)\n- [GLM-5.3-Flash vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-397b.md)\n- [GLM-5.3-Flash vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ornith-1-5-9b.md)\n- [GLM-5.3-Flash vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-otel-2-0-llm-31b-it.md)\n- [GLM-5.3-Flash vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen-agentworld-35b-a3b.md)\n- [GLM-5.3-Flash vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-30b-a3b-instruct-2507.md)\n- [GLM-5.3-Flash vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-4b-instruct-2507.md)\n- [GLM-5.3-Flash vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-0-8b.md)\n- [GLM-5.3-Flash vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-122b-a10b.md)\n- [GLM-5.3-Flash vs Qwen3.5-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-2b.md)\n- [GLM-5.3-Flash vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-397b-a17b.md)\n- [GLM-5.3-Flash vs Qwen3.5-4B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-4b.md)\n- [GLM-5.3-Flash vs Qwen3.5-9B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-5-9b.md)\n- [GLM-5.3-Flash vs Qwen3.6-27B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-27b.md)\n- [GLM-5.3-Flash vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-6-35b-a3b.md)\n- [GLM-5.3-Flash vs Qwen3.8-27B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-27b.md)\n- [GLM-5.3-Flash vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-8-flash-next.md)\n- [GLM-5.3-Flash vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-30b-a3b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-coder-next.md)\n- [GLM-5.3-Flash vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-omni-30b-a3b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-2b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-30b-a3b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-32b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-4b-instruct.md)\n- [GLM-5.3-Flash vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwen3-vl-8b-instruct.md)\n- [GLM-5.3-Flash vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-qwopus3-8-27b-flash-v2.md)\n- [GLM-5.3-Flash vs Recursive Flint](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-recursive-flint.md)\n- [GLM-5.3-Flash vs Ripple-65B Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-ripple-65b-preview.md)\n- [GLM-5.3-Flash vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-sensenova-loop-9b-preview.md)\n- [GLM-5.3-Flash vs SmolLM3-3B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-smollm3-3b.md)\n- [GLM-5.3-Flash vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-spark-x2-6-4b.md)\n- [GLM-5.3-Flash vs Step 3.7 Flash](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-step-3-7-flash.md)\n- [GLM-5.3-Flash vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-27b.md)\n- [GLM-5.3-Flash vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-swift-1-5-qwen3-8-flash-next.md)\n- [GLM-5.3-Flash vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-thinkingcap-qwen3-8-27b.md)\n- [GLM-5.3-Flash vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2.md)\n- [GLM-5.3-Flash vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-2b.md)\n- [GLM-5.3-Flash vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-wevisone-vl-4b.md)\n- [GLM-5.3-Flash vs ZAYA1-8B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-zaya1-8b.md)\n- [GLM-5.3 vs GLM-5.3-Flash](https://www.anchorterminal.com/compare/glm-5-3-vs-glm-5-3-flash.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Devstral Small 2 vs GLM-5.3-Flash", "url": "" } ], "description": "GLM-5.3-Flash scores 65.1 (B) to Devstral Small 2's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Devstral Small 2 C 61", "GLM-5.3-Flash B 65.1", "scores" ], "h1": "Devstral Small 2 vs GLM-5.3-Flash", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/devstral-small-2-vs-glm-5-3-flash", "published": "2026-10-01", "section": "tools", "title": "Devstral Small 2 vs GLM-5.3-Flash for AI agents (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-glm-5-3-flash" }, "tokens": { "markdown": 9600, "slim": 780 }, "version": 1 }